On Fri, Apr 1, 2016 at 2:48 PM, Wido den Hollander wrote:
> Somehow the PG got corrupted on one of the OSDs and it kept crashing on a
> single
> object.
Vaguely reminds me of the E2BIG from that one issue way-back-when in
Dumpling
> Op 1 april 2016 om 1:28 schreef Goncalo Borges :
>
>
> Hi Mart, Wido...
>
> A disclaimer: Not really an expert, just a regular site admin sharing my
> experience.
>
Thanks!
> At the beginning of the thread you give the idea that only osd.68 has
> problems
Hi Mart, Wido...
A disclaimer: Not really an expert, just a regular site admin sharing my
experience.
At the beginning of the thread you give the idea that only osd.68 has
problems dealing with the problematic PG 3.117. If that is indeed the
case, you could simply mark that osd.68 down and
Hello,
Well unfortunately the problem is not really solved. Yes, we managed to
get to a good health state at some point, when a client hits some
specific data, the osd process crashes with below errors. The 3 OSD
which handle 3.117, the PG with problems, are currently down and
reweighted them